INDEX

Explanations

legal terms and consent-related phrases

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anzi

-0.17

ãĥ³ãĤº

-0.16

gles

-0.15

 Dove

-0.15

ingers

-0.15

ates

-0.14

 playable

-0.14

|--

-0.14

 Ulus

-0.14

 globalization

-0.13

POSITIVE LOGITS

lere

0.16

riad

0.15

aine

0.15

ë²Į

0.15

mÃŃn

0.14

ä¸Ī

0.14

.AutoComplete

0.14

reeting

0.14

wart

0.14

unt

0.14

Activations Density 0.000%

legal terms and consent-related phrases

No Comments

No Known Activations